INDEX

Explanations

references to names or titles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

name, rating, or FAM

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arroll

-0.48

 Hälfte

-0.47

 cafetería

-0.45

 policiers

-0.43

 IPCC

-0.40

 amortigu

-0.40

 McCulloch

-0.40

pelo

-0.40

 Abril

-0.40

toolkit

-0.40

POSITIVE LOGITS

名

2.31

名

1.70

的名

1.52

명

1.33

の名

1.30

명

1.28

名は

1.17

名的

1.17

 name

1.15

名の

1.11

Activations Density 0.001%

references to names or titles

name, rating, or FAM

No Comments

No Known Activations

references to names or titles

name, rating, or FAM

No Comments

No Known Activations